GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
read the original abstract
We propose a new network architecture, Gated Attention Networks (GaAN), for learning on graphs. Unlike the traditional multi-head attention mechanism, which equally consumes all attention heads, GaAN uses a convolutional sub-network to control each attention head's importance. We demonstrate the effectiveness of GaAN on the inductive node classification problem. Moreover, with GaAN as a building block, we construct the Graph Gated Recurrent Unit (GGRU) to address the traffic speed forecasting problem. Extensive experiments on three real-world datasets show that our GaAN framework achieves state-of-the-art results on both tasks.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.
-
Graph Star Net for Generalized Multi-Task Learning
GraphStar is a new GNN that adds star nodes and relay attention to achieve non-local representations for node, graph, and link tasks, claiming 2-5% gains over prior SOTA on benchmarks.
-
GMENet: Generative Mixture of Experts Network for Multi-Center Glioma Diagnosis with Incomplete Imaging Sequences
GMENet synthesizes missing MRI sequences with gated cross-attention and fuses dual-sequence features via confidence-aware mixture-of-experts for improved glioma diagnosis on incomplete multi-center data.
-
A Global-Local Graph Attention Network for Traffic Forecasting
GLGAT uses global-local graph attention with pairwise encoding and event-based adjacency to capture spatio-temporal traffic correlations and reports competitive results on two real-world datasets.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.